Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than expected, thereby yielding both positive and negative signals for training. However, existing approaches often mix them indiscriminately, especially in the early stages, leading to ambiguous guidance and limited gains. To address this issue, we propose CAPO (Curriculum Advantage Policy Optimization), an adaptive curriculum mechanism based on advantage signals. The proposed mechanism bootstraps imitation learning with positive-only advantage samples to establish robust foundations, and subsequently introduces negative signals to cultivate discriminative capabilities, thereby improving generalization across complex scenarios. Compatible with diverse optimization methods including GRPO, PPO, RLOO, and Reinforce++, our method consistently achieves stable and significant improvements in mathematical reasoning tasks, and further generalizes effectively to multimodal Graphical User Interface (GUI) reasoning scenarios, establishing itself as a versatile and robust optimization paradigm.

Human motion video generation has garnered significant research interest due to its broad applications, enabling innovations such as photorealistic singing heads or dynamic avatars that seamlessly dance to music. However, existing surveys in this field focus on individual methods, lacking a comprehensive overview of the entire generative process. This paper addresses this gap by providing an in-depth survey of human motion video generation, encompassing over ten sub-tasks, and detailing the five key phases of the generation process: input, motion planning, motion video generation, refinement, and output. Notably, this is the first survey that discusses the potential of large language models in enhancing human motion video generation. Our survey reviews the latest developments and technological trends in human motion video generation across three primary modalities: vision, text, and audio. By covering over two hundred papers, we offer a thorough overview of the field and highlight milestone works that have driven significant technological breakthroughs. Our goal for this survey is to unveil the prospects of human motion video generation and serve as a valuable resource for advancing the comprehensive applications of digital humans.

Designing a robust air transportation network is critical for aviation activities to maintain highly efficient operations. Given certain total route cost, designing a strategy to improve the robustness of the network is a challenging issue. In this paper, first, a comparison experiment based on a small example shows the total effective resistance is a superior measure satisfying two critical criteria that other measures do not satisfy. Consequently, we explicitly formulate the network optimization problem as the minimization of total effective resistance under several constraints. The problem is often too time-consuming to solve to the optimal by exact methods. To achieve better efficiency, we propose a convex relaxation method for medium-scale networks making use of the problem properties. For large-scale networks, a clustering based convex relaxation method, reducing the dimensions of the network via selecting critical airports, is further proposed. To demonstrate the efficiency and efficacy of the proposed methods, simulations are performed on nine typical scale-free network and two real air transportation networks including Jetstar Asia Airway and domestic American Airlines.Note to Practitioners—The crucial need for designing robust air transportation networks in the aviation industry serves as the impetus for this work. The application scenarios range from the design of airport and flight operation networks for airlines, to air traffic networks with airways and waypoints, extending to drone cargo networks. An essential characteristic of a well-designed network is its ability to preserve connectivity, as much as possible, when it experiences disruptions such as flight cancellation or airway navigation equipment failure. The paper presents an argument for using total effective resistance as the key measure of network robustness, showing it to outperform other measures. We’ve developed specialized algorithms that leverage the unique properties of this optimization problem to minimize the total effective resistance of air transportation networks subject to certain total route cost to enhance the network structure. Although this study focuses on air transportation networks, the applicability of the algorithms extends beyond this field. Practitioners can apply them in other scenarios to design robust networks in various aviation operations.

The neural radiance field (NeRF) achieved remarkable success in modeling 3D scenes and synthesizing high-fidelity novel views. However, existing NeRF-based methods focus more on making full use of high-resolution images to generate high-resolution novel views, but less considering the generation of high-resolution details given only low-resolution images. In analogy to the extensive usage of image super-resolution, NeRF super-resolution is an effective way to generate low-resolution-guided high-resolution 3D scenes and holds great potential applications. Up to now, such an important topic is still under-explored. In this article, we propose a NeRF super-resolution method, named Super-NeRF, to generate high-resolution NeRF from only low-resolution inputs. Given multi-view low-resolution images, Super-NeRF constructs a multi-view consistency-controlling super-resolution module to generate various view-consistent high-resolution details for NeRF. Specifically, an optimizable latent code is introduced for each input view to control the generated reasonable high-resolution 2D images satisfying view consistency. The latent codes of each low-resolution image are optimized synergistically with the target Super-NeRF representation to utilize the view consistency constraint inherent in NeRF construction. We verify the effectiveness of Super-NeRF on synthetic, real-world, and even AI-generated NeRFs. Super-NeRF achieves state-of-the-art NeRF super-resolution performance on high-resolution detail generation and cross-view consistency.

3D facial editing, a longstanding task in computer vision with broad applications, is expected to fast and intuitively manipulate any face from arbitrary viewpoints following the user's will. Existing works have limitations in terms of intuitiveness, generalization, and efficiency. To overcome these challenges, we propose FaceEdit3D, which allows users to directly manipulate 3D points to edit a 3D face, achieving natural and rapid face editing. After one or several points are manipulated by users, we propose the tri-plane warping to directly deform the view-independent 3D representation. To address the problem of distortion caused by tri-plane warping, we train a warp-aware encoder to project the warped face onto a standardized latent space. In this space, we further propose directional latent editing to mitigate the identity bias caused by the encoder and realize the disentangled editing of various attributes. Extensive experiments show that our method achieves superior results with rich facial details and nice identity preservation. Our approach also supports general applications like multi-attribute continuous editing and cat/car editing. The project website is https://cyh-sj.github.io/FaceEdit3DI.

The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion capture standards. In addition, it is a challenging task due to the weak correlation between speech and gestures. To address these problems, we present UnifiedGesture, a novel diffusion model-based speech-driven gesture synthesis approach, trained on multiple gesture datasets with different skeletons. Specifically, we first present a retargeting network to learn latent homeomorphic graphs for different motion capture standards, unifying the representations of various gestures while extending the dataset. We then capture the correlation between speech and gestures based on a diffusion model architecture using cross-local attention and self-attention to generate better speech-matched and realistic gestures. To further align speech and gesture and increase diversity, we incorporate reinforcement learning on the discrete gesture units with a learned reward function. Extensive experiments show that UnifiedGesture outperforms recent approaches on speech-driven gesture generation in terms of CCA, FGD, and human-likeness.

Even though conventional wisdom claims that in order to improve viewer engagement, the cloud-edge providers should serve the viewers with the nearest edge nodes, however, we show that doing this for crowdsourced live streaming (CLS) services can introduce significant costs inefficiency. In this paper, we first carry out large-scale measurement analysis by using the real-world service data from Huawei Cloud, a representative cloud-edge provider in China. We observe that the massive number of channels has proposed great burdens to the operating expenditure of the cloud-edge providers, and most importantly, unbalanced viewer distribution makes the edge nodes suffer significant costs inefficiency. To tackle the above concerns, we proposeAggCast, a novel CLS scheduling framework to optimize the edge node utilization for the cloud-edge provider. The core idea ofAggCastis to aggregate some viewers that are initially scattered on different regions, and assign them to fewer pre-selected nodes, thereby reducing bandwidth costs. In particular, by integrating the useful insights obtained from our large-scale measurement,AggCastcan not only ensure that quality of experience (QoS) does not suffer degradation, but also satisfy the systematic requirements of CLS services.AggCasthas been A/B tested and fully deployed. The online and trace-driven experiments show that, compared to the most prevalent method,AggCastsaves over 16.3%back-to-source(BTS) bandwidth costs while significantly improving QoS (startup latency, stall frequency and stall time are reduced over 12.3%, 4.57% and 3.91%, respectively).

Cloud providers often build a geo-distributed cloud from multiple datacenters in different geographic regions, to serve tenants at different locations. The tenants that run large scale applications often reserve resources based on their peak loads in the region close to the end users to handle the ever changing application load, wasting a large amount of resources. We therefore characterize the VM request patterns of the top tenants in our production public geo-distributed cloud, and open-source the VM request traces in four months from the top 20 tenants of our cloud. The characterization shows that the resource usage of large tenants has various temporal and spatial patterns on the dimensions of time series, regions, and VM types, and has the potential of peak shaving between different tenants to further reduce the resource reservation cost. Based on the findings, we propose a resource reservation and VM request scheduling scheme named ROS to minimize the resource reservation cost while satisfying the VM allocation requests. Our experiments show that ROS reduces the overall deployment cost by 75.4% and the reservation resources by 60.1%, compared to the tenant-specified reservation strategy.

Conventional wisdom claims that in order to improve viewer engagement, the cloud-edge providers should serve the viewers with the nearest edge nodes, however, we show that doing this for crowdsourced live streaming (CLS) services can introduce significant costs inefficiency. We observe that the massive number of channels has greatly burdened the operating expenditure of the cloud-edge providers, and most importantly, unbalanced viewer distribution makes the edge nodes suffer significant costs inefficiency. To tackle the above concerns, we propose AggCast, a novel CLS scheduling framework to optimize the edge node utilization for the cloud-edge provider. The core idea of AggCast is to aggregate some viewers who are initially scattered on different regions, and assign them to fewer pre-selected nodes, thereby reducing bandwidth costs. In particular, by leveraging the insights obtained from our large-scale measurement, AggCast can not only ensure quality of experience (QoS), but also satisfy the systematic requirements of CLS services. AggCast has been A/B tested and fully deployed in a top cloud-edge provider in China for over eight months. The online and trace-driven experiments show that, compared to the common practice, AggCast can save over 15% back-to-source (BTS) bandwidth costs while having no negative impacts on QoS.

Designing a robust air transportation network is an ongoing research effort that seeks to improve the extent of a network being connected against failures and attacks. The total effective resistance can be a promising measure for network robustness as demonstrated by case studies conducted in this paper. To enhance the robustness of air transportation networks, we consider to solve a flight route selection problem in which a set of routes is chosen from a candidate route set to minimize the utility function defined by the total effective resistance. Since it is an integer nonlinear programming problem, to balance the tradeoff between optimality performance and computational efficiency, two methods that implement the total effective resistance are developed to suit different network scales. For small/medium-scale networks, we develop an interior-point method based on convex relaxation and duality gap, which achieves a near optimality performance within acceptable time. For large-scale networks, we develop an accelerated greedy algorithm based on proved monotone submodularity, which can substantially reduce the computation time in deriving a good solution with a guaranteed optimality gap. Their optimality performance and computational efficiency are verified and compared through numerical results. Moreover, three case studies from real-world examples are also performed to demonstrate the application of the proposed methods for different network scales.